Artificial intelligence challenge of discriminating cutaneous arteritis and polyarteritis nodosa based on hematoxylin-and-eosin images of skin biopsy specimens.

Journal: Pathology, research and practice
PMID:

Abstract

Diseases that develop necrotizing vasculitis of cutaneous muscular arteries include cutaneous arteritis (CA) and polyarteritis nodosa (PAN). It is difficult to distinguish them based on skin biopsy findings alone. This study demonstrated that artificial intelligence (AI) can discriminate them based on skin biopsy findings and revealed where AI focuses on the image. Ninety-three hematoxylin-and-eosin images of CA and 19 PAN images were used. Among them, 85 CA and 17 PAN images were used to train AI; thereafter, AI was challenged to classify the remaining images. The same test images were evaluated by 26 pathologists with different years of experience. AI accuracy was 75.2 %, whereas that of pathologists was 42.8 %. Gradient-weighted class activation mapping (Grad-CAM) indicated that AI focused on connective tissues around the affected vessels rather than the affected vessels. Twenty-two of the 26 pathologists were randomly divided into two groups of 11 each, one of which referred to Grad-CAM images and was challenged in the second-round test of images different from the first round. The accuracy significantly improved after referring to Grad-CAM images, whereas it was equivalent to the first round without referring to Grad-CAM images. In the survey after the second-round test, pathologists who referred to Grad-CAM images suggested that inflammation and fibrosis in the surrounding connective tissues in PAN might be abundant compared to CA. AI may be useful for histological differentiation between CA and PAN and can help pathologists improve the ability of discriminating CA and PAN based on histological findings of skin biopsy specimens.

Authors

  • Wataru Kashiwa
    Graduate School of Medicine, Hokkaido University, Sapporo, Japan.
  • Kenji Hirata
    Department of Diagnostic Imaging, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan.
  • Hiroki Endo
    Deaprtment of Diagnostic Imaging, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan.
  • Kohsuke Kudo
    Departments of Diagnostic Imaging, Hokkaido University Graduate School of Medicine, kita 15, nishi 7, kita-ku, Sapporo, Hokkaido, 060-8638, Japan.
  • Chietsugu Katoh
    Graduate School of Biomedical Science and Engineering, School of Medicine, Hokkaido University, N15 W7, Kita-ku, Sapporo, 0608638, Japan.
  • Tamihiro Kawakami
    Faculty of Health Sciences, Hokkaido University , Sapporo , Japan.
  • Hiroyuki Kanno
    Department of Pathology, Shinshu University School of Medicine, Nagano, Japan.
  • Kei Takahashi
    Faculty of Information Engineering, Fukuoka Institute of Technology, Fukuoka, Japan.
  • Tatsuhiko Miyazaki
    Department of Pathology, Gifu University Hospital, Gifu, Japan.
  • Eiji Ikeda
  • Toshiaki Oharaseki
    Department of Pathology, Toho University Ohashi Medical Center, Tokyo, Japan.
  • Yayoi Ogawa
    Hokkaido Renal Pathology Center, Sapporo, Japan.
  • Mitsuho Onimaru
    Division of Pathophysiological and Experimental Pathology, Department of Pathology, Graduate School of Medical Sciences, Kyushu University, Fukuoka, Japan.
  • Mie Kurata
    Department of Analytical Pathology, Ehime University Graduate School of Medicine, Ehime, Japan.
  • Daigo Nakazawa
    Division of Rheumatology, Endocrinology and Nephrology, Hokkaido University Graduate School of Medicine , Sapporo , Japan.
  • Eri Muso
    Department of Nephrology and Dialysis, Medical Research Institute Kitano Hospital, PIIF Tazuke Kofukai, Osaka, Japan.
  • Yuka Nishibata
    Department of Medical Laboratory Science, Faculty of Health Sciences, Hokkaido University, Sapporo, Japan.
  • Sakiko Masuda
    Department of Pathology, Hokkaido University Graduate School of Medicine , Sapporo , Japan.
  • Utano Tomaru
    Department of Dermatology, St. Marianna University School of Medicine , Kawasaki , Japan.
  • Yoshihiro Matsuno
    Deaprtment of Surgical Pathology, Hokkaido University Hospital, Sapporo, Japan.
  • Shunsuke Furuta
    Department of Allergy and Clinical Immunology, Chiba University Hospital, Chiba, Japan.
  • Yoshiyuki Abe
    Department of Internal Medicine and Rheumatology, Juntendo University School of Medicine, Tokyo, Japan.
  • Naoto Tamura
    Department of Internal Medicine and Rheumatology, Juntendo University School of Medicine, Tokyo, Japan.
  • Masayoshi Harigai
    Division of Rheumatology, Department of Internal Medicine, Tokyo Women's Medical University School of Medicine, Tokyo, Japan.
  • Akihiro Ishizu
    Department of Pathology, Hokkaido University Graduate School of Medicine , Sapporo , Japan.